model-optimization

model-optimization copied to clipboard

Q1. Can I train a model from scratch using Quantization aware training? Or It can only be used as fine-tuning method ? Q2. Are QFormats for weight tensors decided before...

abhiagwl4262

modify_model_interface removing input float tensor is not completed, memory allocator occupied this dummy tensor

2

### 1. System information TFLM Tensorflow r2.5 ### 2. Code code in tensorflow\tensorflow\lite\tools\optimize\modify_model_interface.cc Function: RemoveInputTensor `code: c // Removes the input tensor and the related operator. for (auto tot :...

jimch3n

Internal changes

copybara-service[bot]

Internal changes

copybara-service[bot]

WARNING:tensorflow:AutoGraph could not transform <tensorflow_model_optimization.python.core.quantization.keras.quantizers.AllValuesQuantizer object at 0x7f92927f3f90> and will run it as-is.

1

Hey, I am using the quantization Wrapper and keep getting the following warning: ``` WARNING:tensorflow:AutoGraph could not transform and will run it as-is. Please report this to the TensorFlow team....

lovodkin93

Depthwise convolution min_max dimension

2

Hello, i met a new issue when i tried to translate the weight of a pytorch model after QAT to a keras model. My model contains a depthwise convolution layer...

ai1361720220000

TFLite quantization, the int tflite model is much slower than the float tflite model

5

I converted Pytorch model to onnx model, and then to tensorflow model, I convert tensorflow model to float tflite model and int tflite model(with post training quantization). Currently, my int...

SkylerZheng

Is there a way to do symmetric quantization for activations in post-training quantization

1

https://tensorflow.google.cn/lite/performance/quantization_spec from this document we can see the post-training quantization do asymmetric quantization for activations, do symmetric quantization for wieghts. I follow this guide: https://tensorflow.google.cn/lite/performance/post_training_integer_quant do full int8 quantization for...

Lemiron24

Performance issue in the program

2

Hello, I found a performance issue in the definition of `encode`, tensorflow_model_optimization/python/core/internal/tensor_encoding/stages/research/kashin.py, [tf.cast](https://github.com/tensorflow/model-optimization/blob/d1559484e6e2f7147e38077813d1b0511d407117/tensorflow_model_optimization/python/core/internal/tensor_encoding/stages/research/kashin.py#L201) will be calculated repeatedly during program execution, resulting in reduced efficiency. I think it should be created...

DLPerf

Quantization aware training with mask_rcnn model error: tensorflow.python.framework.errors_impl.NotFoundError: Key SecondStageFeatureExtractor_1/InceptionV2/Mixed_5a/Branch_0/Conv2d_0a_1x1/act_quant/max not found in checkpoint [[{{node save/RestoreV2}}]]

1

### 1. System information - OS Platform and Distribution (e.g., Linux Ubuntu 16.04): Linux Ubuntu 18.04 - TensorFlow installation (pip package or built from source): pip - TensorFlow library (version,...

JiashuGuo